Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pher
    -0.07
    gue
    -0.07
     file
    -0.07
    _UN
    -0.07
     withdrew
    -0.07
    unbind
    -0.06
     summon
    -0.06
    GET
    -0.06
     Kits
    -0.06
    endon
    -0.06
    POSITIVE LOGITS
     DeepCopy
    0.07
    有效
    0.07
    weathermap
    0.07
     imshow
    0.06
    พวก
    0.06
    ($(".
    0.06
    [];
↵
    0.06
    직
    0.06
    ！",
    0.06
    ："+
    0.06
    Act Density 0.041%

    No Known Activations